{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/load-metrics","entry":"load_metrics","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":6,"n_papers_ran":3,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.12652","paper":"/paper/arxiv-2605-12652","title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"viviable/mopd_code","path":"analysis/plot_teacher_metrics.py","file_url":"https://github.com/viviable/mopd_code/blob/HEAD/analysis/plot_teacher_metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"aebe25129f6e22f7","mcp_get_code":{"code_sha256":"aebe25129f6e22f7"}},{"arxiv_id":"2512.01428","paper":"/paper/arxiv-2512-01428","title":"Masked Symbol Modeling for Demodulation of Oversampled Baseband Communication Signals in Impulsive Noise-Dominated Channels","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"OguzBedir/Masked_Symbol_Modeling","path":"plot_metrics.py","file_url":"https://github.com/OguzBedir/Masked_Symbol_Modeling/blob/HEAD/plot_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"183f947b5ddae1d5","mcp_get_code":{"code_sha256":"183f947b5ddae1d5"}},{"arxiv_id":"2511.18891","paper":"/paper/arxiv-2511-18891","title":"Reproducibility Study of: Large Language Model Bayesian Optimization","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"spagnoloG/llambo-reproducibility","path":"LLAMBO/plot_figure2_full.py","file_url":"https://github.com/spagnoloG/llambo-reproducibility/blob/HEAD/LLAMBO/plot_figure2_full.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce7b65c82f4f272d","mcp_get_code":{"code_sha256":"ce7b65c82f4f272d"}},{"arxiv_id":"2404.18812","paper":"/paper/efficient-inverted-indexes-for-approximate","title":"Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations","date":"2024-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"castorini/anserini","path":"src/main/python/compare_runs.py","file_url":"https://github.com/castorini/anserini/blob/HEAD/src/main/python/compare_runs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8ea53853b253e05d","mcp_get_code":{"code_sha256":"8ea53853b253e05d"}},{"arxiv_id":"2305.18290","paper":"/paper/direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kidist-amde/ddro-direct-document-relevance-optimization","path":"src/utils/compare_models.py","file_url":"https://github.com/kidist-amde/ddro-direct-document-relevance-optimization/blob/HEAD/src/utils/compare_models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1233495c1bf99438","mcp_get_code":{"code_sha256":"1233495c1bf99438"}},{"arxiv_id":"1804.01523","paper":"/paper/stochastic-adversarial-video-prediction","title":"Stochastic Adversarial Video Prediction","date":"2018-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alexlee-gk/video_prediction","path":"scripts/evaluate.py","file_url":"https://github.com/alexlee-gk/video_prediction/blob/HEAD/scripts/evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5815eb5ba521e8cb","mcp_get_code":{"code_sha256":"5815eb5ba521e8cb"}}]}